Mongolian Speech-to-Text Leaderboard
Whisper large-v3Operating point: openai/whisper-large-v3 (language=mn, task=transcribe) on mps

Whisper large-v3 — Mongolian Speech-to-Text Benchmark

Real results from the Whisper large-v3 Batch API (enhanced operating point, language mn) evaluated across 4 Mongolian datasets and 265 audio samples. Every number below is measured — not marketing. WER, speed, and pricing are shown as-is, brutally honest.

Language:MNDiarization:noneSamples:265Run:Aug 18, 2026, 6:22 AMEndpoint:local (transformers)
06710010.5%
Accuracy

265/265 samples transcribed · 100% success rate

06710089.5%
Word Error Rate

Lower is better · across 265 samples

Headline metrics
Character Error Rate37.4%
Avg speed factor1.29×realtime multiple
Total speed factor1.29×
Avg latency / sample6.0s
Total audio processed1849.3s30.8 min

Pricing

Whisper large-v3 list pricing for batch transcription. No discounts, no negotiated rates applied — the raw per-minute rate.

Per 1k minutes
$0
batch
Per minute
$0.0000
effective
Per 1k min (these 30.8 min)
$0.00
would cost
Open source?
proprietary

Pricing source: Whisper large-v3 public pricing. Duudlaga Flow is shown for context only — this page isolates Whisper large-v3 so the number is not padded by our own product.

WER & CER by dataset

Word and character error rates per dataset. Lower is better — and these are the real Whisper large-v3 numbers, which are weak on Common Voice 24.

Common Voice 24 (MN)
Source dataset →
WER
91.2%
CER
38.8%
Shunya Labs Mongolian Speech
Source dataset →
WER
86.2%
CER
33%
Common Voice 20 (MN)
Source dataset →
WER
94%
CER
41%
Modern Voice
WER
87.7%
CER
37.2%
WERCER

Dataset summary

Aggregate accuracy, speed, and timing for each dataset.

DatasetSourceSamplesSuccessWERCERAccuracySpeedAudio (s)Proc (s)
Common Voice 24 (MN)Hugging Face →5959/5991.2%38.8%8.8%0.72×330.6s456.5s
Shunya Labs Mongolian SpeechHugging Face →6060/6086.2%33%13.8%1.87×645.1s344.8s
Common Voice 20 (MN)Hugging Face →5454/5494%41%6.0%1.13×269.8s238.3s
Modern Voice9292/9287.7%37.2%12.3%1.53×603.8s394.1s

WER vs speed — per sample

Each dot is one audio sample. The sweet spot is the bottom-left (low error, fast). Whisper large-v3 sits high on error for many Common Voice 24 samples.

Per-sample results

Ground truth shown verbatim in the Expected column. The result column highlights only the words Whisper large-v3 got wrong, in red — no strikethrough/swap gymnastics, just the mistakes.

265 rows
redwrong word in the resultplaincorrectly transcribedExpected column shown verbatim as ground truth
#AudioSampleDatasetExpected (ground truth)Whisper large-v3 resultWERCERI/D/S
1btsee_0001Common Voice 24 (MN)Гэхдээ амьсгал хураахаасаа өмнө танд мэдэж байгаагаа хэлье.Кэлтээ амсгол түрээ хасаа омон танд мэдэж байгаа хэлээ.87.5%32.8%1/0/6
2btsee_0002Common Voice 24 (MN)Надад заяасан аз жаргал гэдэг ердөө гуравхан сарын хугацаатай байсан гэж үү?Надзай асан аджирал гэдэгээрдээ үрхүн сарай хүгцадтай байсан гэж бүх.83.3%33.3%0/2/8
3btsee_0003Common Voice 24 (MN)Одоо бид өөрсдөө өвчин эмгэгээсээ салахыг хичээцгээе.Атаах тээ төрч төрч энрээгээсээ салхих чигцгээ.100.0%53.8%0/0/7
4btsee_0004Common Voice 24 (MN)Би бол голдуу хээрээр гэр, хэцээр дэр хийж явдаг хүн.Би босголту хэрээр гэр хэцэр дэрхийж ябдог хүн.70.0%17.6%0/2/5
5btsee_0005Common Voice 24 (MN)Хан хурмаст уурлаж, Болдоггүй Бор өвгөнийг хор луугаараа ниргүүлэхээр явуулжээ.Ханхурмас дуу орлос болдгой бараа үгэнээ 2 лоогуу арны эргүйлэхээр ягалж байна.120.0%51.9%2/0/10
6btsee_0006Common Voice 24 (MN)Алив наашаа ороод ир гээд гэртээ оров.Аж байнааша ородор, гэдгэжтэй оров.85.7%35.1%0/2/4
7btsee_0007Common Voice 24 (MN)Өө өндөр дээдэс таны тухайд би баталж чадахгүй.Уу, үндэр дээд таныи тухууд би бааталг чалтахгүй.87.5%28.3%0/0/7
8btsee_0008Common Voice 24 (MN)Харин гурав дахь удаагаас эхлэн хүмүүсийг сонирхож эхлэв.Харин 3-тэг хуудагаса эхлэн хүмүүстэг сайнархаж гэлэв.75.0%35.7%0/0/6
9btsee_0009Common Voice 24 (MN)Та нар очингуутаа шөл л өгч үз.Танр очингууд шүүллэл үхж байз.100.0%50.0%0/2/5
10btsee_0010Common Voice 24 (MN)Ерөөсөө литр үйлдвэрээсээ салаагүй явсан юм чинь.Ерөөсөөл үүлтүрөссээ салаагуу ябсан имч нь.100.0%33.3%0/1/6
Page 1 of 27

Methodology

How these numbers were produced.

Provider: Whisper large-v3 (OpenAI Whisper large-v3 open weights run locally with an explicit Mongolian language token — the reference open-source ASR baseline.).

Endpoint local (transformers). Language mn. Operating point openai/whisper-large-v3 (language=mn, task=transcribe) on mps. Diarization none.

Datasets: Common Voice 24 (MN), Shunya Labs Mongolian Speech, Common Voice 20 (MN), Modern Voice — 265 samples, 1849.3s of audio total.

Dataset source URLs:

Metrics: WER and CER are computed with a standard word/character Levenshtein alignment, normalized for case and punctuation. Accuracy = 100 − WER. Speed factor = audio duration ÷ processing time (× realtime). All requests are real Whisper large-v3 Batch API calls, not cached or simulated.

Diff highlighting: The result column aligns to the ground truth and colors every substitution and insertion red. Deletions (words missing from the result) are not shown in the result column — the Expected column already holds the full ground truth as-is.

Generated by the Whisper large-v3 Benchmark Runner · Whisper large-v3 Batch API v2 · run Aug 18, 2026, 6:22 AM